Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7115. Min Range: -3.7115

Max Act: 3.7115. Min Act: -0.0001

Data Index: 616196 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.7115. Min Range: -3.7115

Max Act: 3.4127. Min Act: -0.0001

Data Index: 53543 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.7241. Min Act: -0.0001

Data Index: 1070175 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.4982. Min Act: -0.0001

Data Index: 125338 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.5683. Min Act: -0.0001

Data Index: 131114 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.2240. Min Act: -0.0001

Data Index: 1171590 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.4159. Min Act: -0.0001

Data Index: 565462 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.1362. Min Act: -0.0001

Data Index: 383873 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.1963. Min Act: -0.0001

Data Index: 1201727 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.1993. Min Act: -0.0001

Data Index: 393374 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.1639. Min Act: -0.0001

Data Index: 239889 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.9972. Min Act: -0.0001

Data Index: 385737 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.9702. Min Act: -0.0001

Data Index: 100785 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.0624. Min Act: -0.0001

Data Index: 1157760 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.1606. Min Act: -0.0001

Data Index: 618989 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.8559. Min Act: -0.0001

Data Index: 277920 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.7115. Min Range: -3.7115

Max Act: 2.2535. Min Act: -0.0001

Data Index: 694502 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.9012. Min Act: -0.0001

Data Index: 220936 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.9935. Min Act: -0.0001

Data Index: 164827 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 3.7115. Min Range: -3.7115

Max Act: 1.9916. Min Act: -0.0001

Data Index: 1037144 (C4 (Web Text))

Max Activating Token Index: 332